William Hugo Aeberhard

TreeNet Tree Water Deficit Forecasting Dataset

Jan Svoboda, Mirko Lukovic, William Hugo Aeberhard, Sophia Etzold et autres

TreeNet Tree Water Deficit Forecasting Dataset provides a snapshot of automated tree dendrometer measurements together with corresponding meteorological data from TreeNet as time-series data. The dataset contains information about growth and drought stress in trees and can be used to assess and …

ch, us (code pays fourni par la source)

TreeNet Tree Water Deficit Forecasting Dataset

Jan Svoboda, Mirko Lukovic, William Hugo Aeberhard, Sophia Etzold et autres

TreeNet Tree Water Deficit Forecasting Dataset provides a snapshot of automated tree dendrometer measurements together with corresponding meteorological data from TreeNet as time-series data. The dataset contains information about growth and drought stress in trees and can be used to assess and …

ch, us (code pays fourni par la source)

Modeling Uncertainty With Engression: A Deep Generative Time-Series Approach

Basil Kraft, Steven Stalder, William Hugo Aeberhard, Nicolás Harrington Ruiz et autres

Deep learning enables precise environmental predictions across spatial and temporal scales. However, reliable uncertainty estimation with generative capabilities remains crucial for actionable forecasting and simulation, yet robust quantification methods remain challenging. Recently, engression, a generative approach for model-agnostic uncertainty quantification, has been …

Modeling Uncertainty With Engression: A Deep Generative Time‐Series Approach

Basil Kraft, Steven Stalder, William Hugo Aeberhard, Nicolás Harrington Ruiz et autres

Abstract Deep learning enables precise environmental predictions across spatial and temporal scales. However, reliable uncertainty estimation with generative capabilities remains crucial for actionable forecasting and simulation, yet robust quantification methods remain challenging. Recently, engression , a generative approach for model‐agnostic uncertainty quantification, …

ch, us (code pays fourni par la source)

Forecasting Tree Water Deficit and Forest Drought Using Explainable Deep Learning

Jan Svoboda, Mirko Lukovic, William Hugo Aeberhard, Sophia Etzold et autres

ch (code pays fourni par la source)

DROP: A scalable deep learning approach for runoff simulation and river routing

Basil Kraft, Martina Kauzlaric, William Hugo Aeberhard, Massimiliano Zappa et autres

In this study, we propose a deep runoff prediction and propagation model (DROP), a framework designed for spatially explicit discharge prediction along the river network with computational efficiency and physical interpretability. DROP consists of three modules: a long short-term memory (LSTM) network …

ch (code pays fourni par la source)

Leveraging crowd-sourced impact data with ML to improve severe weather warnings at MeteoSwiss

Luca Zamagni, William Hugo Aeberhard, Yun Cheng, Evelyn Mühlhofer et autres

MeteoSwiss disseminates its extreme weather warnings through various channels, one of the most important being the MeteoSwiss smart phone app. This app is the most widely used platform for informing the Swiss population, with over 4.8 million installations and a daily user …

ch (code pays fourni par la source)

Data-driven modeling of environmental factors influencing Arctic methanesulfonic acid aerosol concentrations

Jakob Pernov, William Hugo Aeberhard, Michele Volpi, Eliza Harris et autres

Natural aerosol components such as particulate methanesulfonic acid (MSA p ) play an important role in the Arctic climate. However, numerical models struggle to reproduce MSA p concentrations and seasonality. Here we present an alternative data-driven methodology for modeling MSA p at …

au, ch, md, jp, no, dk, us (code pays fourni par la source)

Modeling uncertainty with engression: a deep generative time-series approach

Basil Kraft, Steven Stalder, William Hugo Aeberhard, Nicolás Harrington Ruiz et autres

Deep learning enables precise environmental predictions and simulations across spatial and temporal scales. However, reliable uncertainty estimation with generative capabilities remains crucial for actionable forecasting and simulation, yet robust and simple quantification methods remain challenging. Recently, engression, a generative approach for model-agnostic …

ch (code pays fourni par la source)

Deep learning for efficient semi-distributed streamflow modeling

Basil Kraft, William Hugo Aeberhard, Lukas Gudmundsson

Neural networks are increasingly used in hydrological applications. In streamflow modeling, long short-term memory (LSTM) networks have demonstrated considerable skill in lumped configurations, where hydrological and meteorological properties are averaged at the catchment scale. However, such averaging may mask important sub-catchment dynamics …

ch (code pays fourni par la source)

CH-RUN: a deep-learning-based spatially contiguous runoff reconstruction for Switzerland

Basil Kraft, Michael Schirmer, William Hugo Aeberhard, Massimiliano Zappa et autres

This study presents a data-driven reconstruction of daily runoff that covers the entirety of Switzerland over an extensive period from 1962 to 2023. To this end, we harness the capabilities of deep-learning-based models to learn complex runoff-generating processes directly from observations, thereby …

ch (code pays fourni par la source)

Long-term aerial monitoring of Florida manatees Trichechus manatus latirostris in a diverse Gulf Coast environment

Kerri M. Scolardi, Krystan A. Wilkinson, William Hugo Aeberhard

Situated on Florida’s Gulf Coast, Sarasota County provides critical habitat for manatees in the Southwest region. Prior analysis of the county’s long-term aerial survey database found increasing numbers of manatees using county waterways from 1987 to 2006. Since that study, the region …

us, ch (code pays fourni par la source)